tines-export-to-3b
Pass
Audited by Gen Agent Trust Hub on Oct 9, 2026
Risk Level: SAFEINDIRECT_PROMPT_INJECTIONEXTERNAL_DOWNLOADSCOMMAND_EXECUTION
Full Analysis
- [INDIRECT_PROMPT_INJECTION]: The skill is designed to process external Tines story JSON exports, which serves as a potential vector for indirect prompt injection.
- Ingestion points: The agent ingests Tines story JSON exports to perform migration tasks (SKILL.md).
- Boundary markers: There are no instructions for the agent to use specific delimiters or to disregard potential instructions embedded within the JSON data.
- Capability inventory: The agent has access to tools like
searchConnectorsandconnectStepToApp, and is instructed to generate code for network requests, database access, and SMTP operations. - Sanitization: The instructions do not mention validation or sanitization of the input JSON content before processing or code generation.
- [EXTERNAL_DOWNLOADS]: The skill instructs the agent to fetch documentation from the vendor's official website to guide the migration process.
- Evidence: References to Tines API documentation URLs, such as
https://www.tines.com/llm/docs/api/resources/get.mdandhttps://www.tines.com/llm/docs/api/records/create.md. - [COMMAND_EXECUTION]: The migration process involves generating executable code and configuring system-level connectors.
- Evidence: Instructions to map "Run Script" actions by copying code "straight over" and generating code for HTTP and database interactions.
Audit Metadata